Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Far beyond the annotations, the description discloses the concrete return shape (null platforms plus a review object), the reason the data is voided (CensoredPlanet rows and IODA outages no longer count as block evidence), and residual caveats (verdict unknown, source reports no data date). For a zero-parameter stub this is exactly the behavioral context an agent needs to avoid misreading an empty response as 'no censorship found'.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, none wasted: the reason for the degraded state comes first, then what is actually returned, then the redirect. The opening clause is dense with internal specifics (CensoredPlanet, IODA, Voidly) but those details justify the null result rather than decorate it.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description carries the burden of describing returns — and it does, naming the null platforms and the review object's fields. Combined with the redirect to get_active_incidents, an agent has everything needed to call it correctly or avoid it. Minor gap: it doesn't say whether this state is temporary or when the review concludes.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes no parameters (schema coverage 100%), so the baseline is 4. Nothing in the description contradicts or adds ambiguity to the empty schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description conveys the resource (per-platform block rates / platform scores) and, unusually, its current degraded state: it returns null platforms and a review object rather than rankings. It also names the sibling that should be used for the real need (get_active_incidents). It loses a point only because the operative purpose is buried behind the 'Under review' framing, so an agent skimming the first clause may not immediately register that this tool is a stub.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is an explicit, actionable alternative: 'For citable censorship events use get_active_incidents.' The condition that makes this tool useless (the source no longer accepts those rows as block evidence) is also stated. What's missing is a direct instruction like 'do not call this tool for rankings' — it is strongly implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.